© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 109110
    Prev
    Next
    INDEX
    Explanations

    distinction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entially
    -0.27
    anter
    -0.27
    entine
    -0.26
    uml
    -0.26
    iores
    -0.26
    edia
    -0.25
    antee
    -0.24
     sequ
    -0.24
    esi
    -0.24
    iants
    -0.24
    POSITIVE LOGITS
     Pang
    0.27
    ãĥIJãĤ¹
    0.26
    ilk
    0.26
    Tac
    0.26
    ilon
    0.25
    .Alpha
    0.24
     mav
    0.24
    TypeId
    0.24
    oid
    0.23
    зо
    0.23
    Activations Density 0.196%

    No Known Activations